* Arun R Bharadwaj <arun@xxxxxxxxxxxxxxxxxx> [2009-10-08 15:18:28]: This patch cleans up x86 of all instances of pm_idle. pm_idle which was earlier called from cpu_idle() idle loop is replaced by cpuidle_idle_call. x86 also registers to cpuidle when the idle routine is selected, by populating the cpuidle_device data structure for each cpu. This is replicated for apm module and for xen, which also used pm_idle. Signed-off-by: Arun R Bharadwaj <arun@xxxxxxxxxxxxxxxxxx> --- arch/x86/kernel/apm_32.c | 55 +++++++++++++++++++++++- arch/x86/kernel/process.c | 93 ++++++++++++++++++++++++++---------------- arch/x86/kernel/process_32.c | 3 - arch/x86/kernel/process_64.c | 3 - arch/x86/xen/setup.c | 40 +++++++++++++++++- drivers/acpi/processor_core.c | 9 ++-- drivers/cpuidle/cpuidle.c | 16 ++++--- include/linux/cpuidle.h | 1 8 files changed, 172 insertions(+), 48 deletions(-) Index: linux.trees.git/arch/x86/kernel/process.c =================================================================== --- linux.trees.git.orig/arch/x86/kernel/process.c +++ linux.trees.git/arch/x86/kernel/process.c @@ -9,6 +9,7 @@ #include <linux/pm.h> #include <linux/clockchips.h> #include <linux/random.h> +#include <linux/cpuidle.h> #include <trace/events/power.h> #include <asm/system.h> #include <asm/apic.h> @@ -244,12 +245,6 @@ int sys_vfork(struct pt_regs *regs) unsigned long boot_option_idle_override = 0; EXPORT_SYMBOL(boot_option_idle_override); -/* - * Powermanagement idle function, if any.. - */ -void (*pm_idle)(void); -EXPORT_SYMBOL(pm_idle); - #ifdef CONFIG_X86_32 /* * This halt magic was a workaround for ancient floppy DMA @@ -329,17 +324,15 @@ static void do_nothing(void *unused) } /* - * cpu_idle_wait - Used to ensure that all the CPUs discard old value of - * pm_idle and update to new pm_idle value. Required while changing pm_idle - * handler on SMP systems. + * cpu_idle_wait - Required while changing idle routine handler on SMP systems. * - * Caller must have changed pm_idle to the new value before the call. Old - * pm_idle value will not be used by any CPU after the return of this function. + * Caller must have changed idle routine to the new value before the call. Old + * value will not be used by any CPU after the return of this function. */ void cpu_idle_wait(void) { smp_mb(); - /* kick all the CPUs so that they exit out of pm_idle */ + /* kick all the CPUs so that they exit out of idle loop */ smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(cpu_idle_wait); @@ -387,20 +380,6 @@ static void mwait_idle(void) } /* - * On SMP it's slightly faster (but much more power-consuming!) - * to poll the ->work.need_resched flag instead of waiting for the - * cross-CPU IPI to arrive. Use this option with caution. - */ -static void poll_idle(void) -{ - trace_power_start(POWER_CSTATE, 0); - local_irq_enable(); - while (!need_resched()) - cpu_relax(); - trace_power_end(0); -} - -/* * mwait selection logic: * * It depends on the CPU. For AMD CPUs that support MWAIT this is @@ -518,15 +497,59 @@ static void c1e_idle(void) default_idle(); } +static void (*local_idle)(void); +DEFINE_PER_CPU(struct cpuidle_device, idle_devices); + +struct cpuidle_driver cpuidle_default_driver = { + .name = "cpuidle_default", +}; + +static int local_idle_loop(struct cpuidle_device *dev, struct cpuidle_state *st) +{ + ktime_t t1, t2; + s64 diff; + int ret; + + t1 = ktime_get(); + local_idle(); + t2 = ktime_get(); + + diff = ktime_to_us(ktime_sub(t2, t1)); + if (diff > INT_MAX) + diff = INT_MAX; + ret = (int) diff; + + return ret; +} + +static int setup_cpuidle_simple(void) +{ + struct cpuidle_device *dev; + int cpu; + + if (!cpuidle_curr_driver) + cpuidle_register_driver(&cpuidle_default_driver); + + for_each_online_cpu(cpu) { + dev = &per_cpu(idle_devices, cpu); + dev->cpu = cpu; + dev->states[0].enter = local_idle_loop; + dev->state_count = 1; + cpuidle_register_device(dev); + } + return 0; +} +device_initcall(setup_cpuidle_simple); + void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - if (pm_idle == poll_idle && smp_num_siblings > 1) { + if (local_idle == poll_idle && smp_num_siblings > 1) { printk(KERN_WARNING "WARNING: polling idle and HT enabled," " performance may degrade.\n"); } #endif - if (pm_idle) + if (local_idle) return; if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) { @@ -534,18 +557,20 @@ void __cpuinit select_idle_routine(const * One CPU supports mwait => All CPUs supports mwait */ printk(KERN_INFO "using mwait in idle threads.\n"); - pm_idle = mwait_idle; + local_idle = mwait_idle; } else if (check_c1e_idle(c)) { printk(KERN_INFO "using C1E aware idle routine\n"); - pm_idle = c1e_idle; + local_idle = c1e_idle; } else - pm_idle = default_idle; + local_idle = default_idle; + + return; } void __init init_c1e_mask(void) { /* If we're using c1e_idle, we need to allocate c1e_mask. */ - if (pm_idle == c1e_idle) + if (local_idle == c1e_idle) zalloc_cpumask_var(&c1e_mask, GFP_KERNEL); } @@ -556,7 +581,7 @@ static int __init idle_setup(char *str) if (!strcmp(str, "poll")) { printk("using polling idle threads.\n"); - pm_idle = poll_idle; + local_idle = poll_idle; } else if (!strcmp(str, "mwait")) force_mwait = 1; else if (!strcmp(str, "halt")) { @@ -567,7 +592,7 @@ static int __init idle_setup(char *str) * To continue to load the CPU idle driver, don't touch * the boot_option_idle_override. */ - pm_idle = default_idle; + local_idle = default_idle; idle_halt = 1; return 0; } else if (!strcmp(str, "nomwait")) { Index: linux.trees.git/arch/x86/kernel/process_32.c =================================================================== --- linux.trees.git.orig/arch/x86/kernel/process_32.c +++ linux.trees.git/arch/x86/kernel/process_32.c @@ -40,6 +40,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/kdebug.h> +#include <linux/cpuidle.h> #include <asm/pgtable.h> #include <asm/system.h> @@ -113,7 +114,7 @@ void cpu_idle(void) local_irq_disable(); /* Don't trace irqs off for idle */ stop_critical_timings(); - pm_idle(); + cpuidle_idle_call(); start_critical_timings(); } tick_nohz_restart_sched_tick(); Index: linux.trees.git/arch/x86/kernel/process_64.c =================================================================== --- linux.trees.git.orig/arch/x86/kernel/process_64.c +++ linux.trees.git/arch/x86/kernel/process_64.c @@ -39,6 +39,7 @@ #include <linux/io.h> #include <linux/ftrace.h> #include <linux/dmi.h> +#include <linux/cpuidle.h> #include <asm/pgtable.h> #include <asm/system.h> @@ -142,7 +143,7 @@ void cpu_idle(void) enter_idle(); /* Don't trace irqs off for idle */ stop_critical_timings(); - pm_idle(); + cpuidle_idle_call(); start_critical_timings(); /* In many cases the interrupt that ended idle has already called exit_idle. But some idle Index: linux.trees.git/arch/x86/kernel/apm_32.c =================================================================== --- linux.trees.git.orig/arch/x86/kernel/apm_32.c +++ linux.trees.git/arch/x86/kernel/apm_32.c @@ -2257,6 +2257,56 @@ static struct dmi_system_id __initdata a { } }; +DEFINE_PER_CPU(struct cpuidle_device, apm_idle_devices); + +struct cpuidle_driver cpuidle_apm_driver = { + .name = "cpuidle_apm", +}; + +static int apm_idle_loop(struct cpuidle_device *dev, struct cpuidle_state *st) +{ + ktime_t t1, t2; + s64 diff; + int ret; + + t1 = ktime_get(); + apm_cpu_idle(); + t2 = ktime_get(); + + diff = ktime_to_us(ktime_sub(t2, t1)); + if (diff > INT_MAX) + diff = INT_MAX; + ret = (int) diff; + + return ret; +} + +void __cpuinit setup_cpuidle_apm(void) +{ + struct cpuidle_device *dev; + + if (!cpuidle_curr_driver) + cpuidle_register_driver(&cpuidle_apm_driver); + + dev = &per_cpu(apm_idle_devices, smp_processor_id()); + dev->cpu = smp_processor_id(); + dev->states[0].enter = apm_idle_loop; + dev->state_count = 1; + cpuidle_register_device(dev); +} + +void exit_cpuidle_apm(void) +{ + struct cpuidle_device *dev; + int cpu; + + for_each_online_cpu(cpu) { + dev = &per_cpu(apm_idle_devices, cpu); + cpuidle_unregister_device(dev); + } +} + + /* * Just start the APM thread. We do NOT want to do APM BIOS * calls from anything but the APM thread, if for no other reason @@ -2394,8 +2444,7 @@ static int __init apm_init(void) if (HZ != 100) idle_period = (idle_period * HZ) / 100; if (idle_threshold < 100) { - original_pm_idle = pm_idle; - pm_idle = apm_cpu_idle; + setup_cpuidle_apm(); set_pm_idle = 1; } @@ -2407,7 +2456,7 @@ static void __exit apm_exit(void) int error; if (set_pm_idle) { - pm_idle = original_pm_idle; + exit_cpuidle_apm(); /* * We are about to unload the current idle thread pm callback * (pm_idle), Wait for all processors to update cached/local Index: linux.trees.git/arch/x86/xen/setup.c =================================================================== --- linux.trees.git.orig/arch/x86/xen/setup.c +++ linux.trees.git/arch/x86/xen/setup.c @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/pm.h> +#include <linux/cpuidle.h> #include <asm/elf.h> #include <asm/vdso.h> @@ -151,6 +152,43 @@ void __cpuinit xen_enable_syscall(void) #endif /* CONFIG_X86_64 */ } +DEFINE_PER_CPU(struct cpuidle_device, xen_idle_devices); +struct cpuidle_driver cpuidle_xen_driver = { + .name = "cpuidle_xen", +}; + +static int xen_idle_loop(struct cpuidle_device *dev, struct cpuidle_state *st) +{ + ktime_t t1, t2; + s64 diff; + int ret; + + t1 = ktime_get(); + xen_idle(); + t2 = ktime_get(); + + diff = ktime_to_us(ktime_sub(t2, t1)); + if (diff > INT_MAX) + diff = INT_MAX; + ret = (int) diff; + + return ret; +} + +void __cpuinit setup_cpuidle_xen(void) +{ + struct cpuidle_device *dev; + + if (!cpuidle_curr_driver) + cpuidle_register_driver(&cpuidle_xen_driver); + + dev = &per_cpu(xen_idle_devices, smp_processor_id()); + dev->cpu = smp_processor_id(); + dev->states[0].enter = xen_idle_loop; + dev->state_count = 1; + cpuidle_register_device(dev); +} + void __init xen_arch_setup(void) { struct physdev_set_iopl set_iopl; @@ -186,7 +224,7 @@ void __init xen_arch_setup(void) MAX_GUEST_CMDLINE > COMMAND_LINE_SIZE ? COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE); - pm_idle = xen_idle; + setup_cpuidle_xen(); paravirt_disable_iospace(); Index: linux.trees.git/drivers/acpi/processor_core.c =================================================================== --- linux.trees.git.orig/drivers/acpi/processor_core.c +++ linux.trees.git/drivers/acpi/processor_core.c @@ -1150,9 +1150,12 @@ static int __init acpi_processor_init(vo * should not use mwait for CPU-states. */ dmi_check_system(processor_idle_dmi_table); - result = cpuidle_register_driver(&acpi_idle_driver); - if (result < 0) - goto out_proc; + + if (!boot_option_idle_override) { + result = cpuidle_register_driver(&acpi_idle_driver); + if (result < 0) + goto out_proc; + } result = acpi_bus_register_driver(&acpi_processor_driver); if (result < 0) Index: linux.trees.git/drivers/cpuidle/cpuidle.c =================================================================== --- linux.trees.git.orig/drivers/cpuidle/cpuidle.c +++ linux.trees.git/drivers/cpuidle/cpuidle.c @@ -224,16 +224,22 @@ void cpuidle_disable_device(struct cpuid EXPORT_SYMBOL_GPL(cpuidle_disable_device); #ifdef CONFIG_ARCH_HAS_CPU_RELAX -static int poll_idle(struct cpuidle_device *dev, struct cpuidle_state *st) +void poll_idle(void) +{ + local_irq_enable(); + while (!need_resched()) + cpu_relax(); +} + +static int poll_idle_loop(struct cpuidle_device *dev, struct cpuidle_state *st) { ktime_t t1, t2; s64 diff; int ret; t1 = ktime_get(); - local_irq_enable(); - while (!need_resched()) - cpu_relax(); + + poll_idle(); t2 = ktime_get(); diff = ktime_to_us(ktime_sub(t2, t1)); @@ -256,7 +262,7 @@ static void poll_idle_init(struct cpuidl state->target_residency = 0; state->power_usage = -1; state->flags = CPUIDLE_FLAG_POLL; - state->enter = poll_idle; + state->enter = poll_idle_loop; } #else static void poll_idle_init(struct cpuidle_device *dev) {} Index: linux.trees.git/include/linux/cpuidle.h =================================================================== --- linux.trees.git.orig/include/linux/cpuidle.h +++ linux.trees.git/include/linux/cpuidle.h @@ -187,6 +187,7 @@ static inline void cpuidle_unregister_go #ifdef CONFIG_ARCH_HAS_CPU_RELAX #define CPUIDLE_DRIVER_STATE_START 1 +extern void poll_idle(void); #else #define CPUIDLE_DRIVER_STATE_START 0 #endif -- To unsubscribe from this list: send the line "unsubscribe linux-arch" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html